[CONTINT-4925] Add new-e2e-containers-k8s-latest job for tracking latest K8s version#44758
Merged
dd-mergequeue[bot] merged 6 commits intomainfrom Jan 15, 2026
Merged
Conversation
triviajon
changed the title
Contributor
Gitlab CI Configuration ChangesModified Jobsnew-e2e-containers new-e2e-containers:
after_script:
- CODECOV_TOKEN=$($CI_PROJECT_DIR/tools/ci/fetch_secret.sh $CODECOV token) || exit
$?; export CODECOV_TOKEN
- $CI_PROJECT_DIR/tools/ci/junit_upload.sh "junit-${CI_JOB_ID}.tgz" "$E2E_RESULT_JSON"
- "if [ -d \"$E2E_COVERAGE_OUT_DIR\" ]; then\n dda inv -- -e coverage.process-e2e-coverage-folders\
\ $E2E_COVERAGE_OUT_DIR\n pip install boto3==1.38.8 # TODO: Remove this before\
\ merging, after dda is bumped in test-infra-definitions\n dda inv -- -e dyntest.compute-and-upload-job-index\
\ --bucket-uri $S3_PERMANENT_ARTIFACTS_URI --coverage-folder $E2E_COVERAGE_OUT_DIR\
\ --commit-sha $CI_COMMIT_SHA --job-id $CI_JOB_ID\nfi\n"
artifacts:
expire_in: 2 weeks
paths:
- $E2E_OUTPUT_DIR
- $E2E_RESULT_JSON
- junit-*.tgz
- $E2E_COVERAGE_OUT_DIR
reports:
annotations:
- $EXTERNAL_LINKS_PATH
when: always
before_script:
- mkdir -p $GOPATH/pkg/mod/cache && tar xJf modcache_e2e.tar.xz -C $GOPATH/pkg/mod/cache
- rm -f modcache_e2e.tar.xz
- mkdir -p ~/.pulumi && tar xJf pulumi_plugins.tar.xz -C ~/.pulumi
- rm -f pulumi_plugins.tar.xz
- mkdir -p $GOPATH/pkg/mod/cache && tar xJf modcache_tools.tar.xz -C $GOPATH/pkg/mod/cache
- rm -f modcache_tools.tar.xz
- dda inv -- -e install-tools
- mkdir -p ~/.aws
- "if [ -n \"$E2E_USE_AWS_PROFILE\" ]; then\n echo Using agent-qa-ci aws profile\n\
\ $CI_PROJECT_DIR/tools/ci/fetch_secret.sh $AGENT_QA_E2E profile >> ~/.aws/config\
\ || exit $?\n # Now all `aws` commands target the agent-qa profile\n export\
\ AWS_PROFILE=agent-qa-ci\nelse\n # Assume role to fetch only once credentials\
\ and avoid rate limits\n echo Assuming ddbuild-agent-ci role\n roleoutput=\"\
$(aws sts assume-role --role-arn arn:aws:iam::669783387624:role/ddbuild-agent-ci\
\ --external-id ddbuild-agent-ci --role-session-name RoleSession)\"\n export\
\ AWS_ACCESS_KEY_ID=\"$(echo \"$roleoutput\" | jq -r '.Credentials.AccessKeyId')\"\
\n export AWS_SECRET_ACCESS_KEY=\"$(echo \"$roleoutput\" | jq -r '.Credentials.SecretAccessKey')\"\
\n export AWS_SESSION_TOKEN=\"$(echo \"$roleoutput\" | jq -r '.Credentials.SessionToken')\"\
\nfi\n"
- $CI_PROJECT_DIR/tools/ci/fetch_secret.sh $AGENT_QA_E2E ssh_public_key_rsa > $E2E_AWS_PUBLIC_KEY_PATH
|| exit $?
- touch $E2E_AWS_PRIVATE_KEY_PATH && chmod 600 $E2E_AWS_PRIVATE_KEY_PATH && $CI_PROJECT_DIR/tools/ci/fetch_secret.sh
$AGENT_QA_E2E ssh_key_rsa > $E2E_AWS_PRIVATE_KEY_PATH || exit $?
- $CI_PROJECT_DIR/tools/ci/fetch_secret.sh $AGENT_QA_E2E ssh_public_key_rsa > $E2E_AZURE_PUBLIC_KEY_PATH
|| exit $?
- touch $E2E_AZURE_PRIVATE_KEY_PATH && chmod 600 $E2E_AZURE_PRIVATE_KEY_PATH &&
$CI_PROJECT_DIR/tools/ci/fetch_secret.sh $AGENT_QA_E2E ssh_key_rsa > $E2E_AZURE_PRIVATE_KEY_PATH
|| exit $?
- $CI_PROJECT_DIR/tools/ci/fetch_secret.sh $AGENT_QA_E2E ssh_public_key_rsa > $E2E_GCP_PUBLIC_KEY_PATH
|| exit $?
- touch $E2E_GCP_PRIVATE_KEY_PATH && chmod 600 $E2E_GCP_PRIVATE_KEY_PATH && $CI_PROJECT_DIR/tools/ci/fetch_secret.sh
$AGENT_QA_E2E ssh_key_rsa > $E2E_GCP_PRIVATE_KEY_PATH || exit $?
- pulumi login "s3://dd-pulumi-state?region=us-east-1&awssdk=v2&profile=$AWS_PROFILE"
- ARM_CLIENT_ID=$($CI_PROJECT_DIR/tools/ci/fetch_secret.sh $E2E_AZURE client_id)
|| exit $?; export ARM_CLIENT_ID
- ARM_CLIENT_SECRET=$($CI_PROJECT_DIR/tools/ci/fetch_secret.sh $E2E_AZURE token)
|| exit $?; export ARM_CLIENT_SECRET
- ARM_TENANT_ID=$($CI_PROJECT_DIR/tools/ci/fetch_secret.sh $E2E_AZURE tenant_id)
|| exit $?; export ARM_TENANT_ID
- ARM_SUBSCRIPTION_ID=$($CI_PROJECT_DIR/tools/ci/fetch_secret.sh $E2E_AZURE subscription_id)
|| exit $?; export ARM_SUBSCRIPTION_ID
- $CI_PROJECT_DIR/tools/ci/fetch_secret.sh $E2E_GCP credentials_json > ~/gcp-credentials.json
|| exit $?
- export GOOGLE_APPLICATION_CREDENTIALS=~/gcp-credentials.json
- dda inv -- -e gitlab.generate-ci-visibility-links --output=$EXTERNAL_LINKS_PATH
- export DD_ENV=nativetest
- export DD_CIVISIBILITY_AGENTLESS_ENABLED=true
- DD_API_KEY=$($CI_PROJECT_DIR/tools/ci/fetch_secret.sh $AGENT_API_KEY_ORG2 token)
|| exit $?; export DD_API_KEY
- export WINDOWS_DDNPM_DRIVER=${WINDOWS_DDNPM_DRIVER:-$(dda inv release.get-release-json-value
"dependencies::WINDOWS_DDNPM_DRIVER" --no-worktree)}
- export WINDOWS_DDPROCMON_DRIVER=${WINDOWS_DDPROCMON_DRIVER:-$(dda inv release.get-release-json-value
"dependencies::WINDOWS_DDPROCMON_DRIVER" --no-worktree)}
image: registry.ddbuild.io/ci/datadog-agent-buildimages/linux$CI_IMAGE_LINUX_SUFFIX:$CI_IMAGE_LINUX
needs:
- go_e2e_deps
- go_e2e_test_binaries
- go_tools_deps
- job: new-e2e-base-coverage
optional: true
- qa_agent
- qa_agent_jmx
- qa_dca
- qa_dogstatsd
parallel:
matrix:
- EXTRA_PARAMS: --run TestKindSuite -c ddinfra:kubernetesVersion=1.19
- EXTRA_PARAMS: --run TestKindSuite -c ddinfra:kubernetesVersion=1.22
- EXTRA_PARAMS: --run TestKindSuite -c ddinfra:kubernetesVersion=1.27
- EXTRA_PARAMS: --run TestKindSuite -c ddinfra:kubernetesVersion=1.29
- - EXTRA_PARAMS: --run TestKindSuite -c ddinfra:kubernetesVersion=v1.34.0@sha256:7416a61b42b1662ca6ca89f02028ac133a309a2a30ba309614e8ec94d976dc5a
- EXTRA_PARAMS: --run TestKindSuite -c ddinfra:osDescriptor=ubuntu:20-04
- EXTRA_PARAMS: --run TestKindSuite -c ddinfra:osDescriptor=ubuntu:22-04
- EXTRA_PARAMS: --run TestDockerSuite
- EXTRA_PARAMS: --run "TestK8S(CEL|Legacy)FilteringSuite"
- EXTRA_PARAMS: --skip "Test(Kind|EKS|ECS|Docker|K8SCELFiltering|K8SLegacyFiltering)Suite"
rules:
- if: $RUN_E2E_TESTS == "off"
when: never
- if: $CI_COMMIT_BRANCH =~ /^mq-working-branch-/
when: never
- if: $RUN_E2E_TESTS == "on"
when: on_success
- if: $CI_COMMIT_BRANCH == "main"
when: on_success
- if: $CI_COMMIT_BRANCH =~ /^[0-9]+\.[0-9]+\.x$/
when: on_success
- if: $CI_COMMIT_TAG =~ /^[0-9]+\.[0-9]+\.[0-9]+-rc\.[0-9]+$/
when: on_success
- changes:
compare_to: $COMPARE_TO_BRANCH
paths:
- .gitlab/test/e2e/e2e.yml
- test/e2e-framework/**/*
- test/new-e2e/go.mod
- go.mod
- flakes.yaml
- release.json
- changes:
compare_to: $COMPARE_TO_BRANCH
paths:
- comp/core/tagger/**/*
- comp/core/workloadmeta/**/*
- comp/core/autodiscovery/listeners/**/*
- comp/core/autodiscovery/providers/**/*
- comp/forwarder/defaultforwarder/**/*
- comp/serializer/**/*
- pkg/aggregator/*/**
- comp/languagedetection/**/*
- pkg/clusteragent/admission/mutate/**/*
- pkg/clusteragent/languagedetection/**/*
- pkg/collector/corechecks/cluster/**/*
- pkg/collector/corechecks/containers/**/*
- pkg/collector/corechecks/containerimage/**/*
- pkg/collector/corechecks/containerlifecycle/**/*
- pkg/collector/corechecks/sbom/**/*
- pkg/sbom/**/*
- pkg/util/clusteragent/**/*
- pkg/util/containerd/**/*
- pkg/util/containers/**/*
- pkg/util/docker/**/*
- pkg/util/ecs/**/*
- pkg/util/kubernetes/**/*
- pkg/util/cgroups/**/*
- pkg/util/trivy/**/*
- test/new-e2e/tests/containers/**/*
- test/new-e2e/go.mod
- go.mod
when: on_success
- changes:
compare_to: $COMPARE_TO_BRANCH
paths:
- pkg/**/*
- cmd/**/*
- comp/**/*
when: on_success
- if: $CI_COMMIT_BRANCH =~ /^mq-working-branch-/
when: never
- allow_failure: true
when: manual
script:
- export IS_DEV_BRANCH="$(dda inv -- -e pipeline.is-dev-branch)"
- DYNAMIC_TESTS_BREAKGLASS=$($CI_PROJECT_DIR/tools/ci/fetch_secret.sh $DYNAMIC_TESTS_BREAKGLASS
value) || exit $?; export DYNAMIC_TESTS_BREAKGLASS
- "if [ \"$DYNAMIC_TESTS_BREAKGLASS\" == \"true\" ] || [ \"$IS_DEV_BRANCH\" == \"\
false\" ] || [ \"$RUN_E2E_TESTS\" == \"on\" ]; then\n export DYNAMIC_TESTS_FLAG=\"\
\"\nfi\n"
- dda inv -- -e new-e2e-tests.run $DYNAMIC_TESTS_FLAG $PRE_BUILT_BINARIES_FLAG $MAX_RETRIES_FLAG
--local-package $CI_PROJECT_DIR/$OMNIBUS_BASE_DIR --result-json $E2E_RESULT_JSON
--targets $TARGETS -c ddagent:imagePullRegistry=669783387624.dkr.ecr.us-east-1.amazonaws.com
-c ddagent:imagePullUsername=AWS -c ddagent:imagePullPassword=$(aws ecr get-login-password)
--junit-tar junit-${CI_JOB_ID}.tgz ${EXTRA_PARAMS} --test-washer --logs-folder=$E2E_OUTPUT_DIR/logs
--logs-post-processing --logs-post-processing-test-depth=$E2E_LOGS_PROCESSING_TEST_DEPTH
stage: e2e
tags:
- arch:amd64
- specific:true
variables:
DYNAMIC_TESTS_FLAG: --impacted
E2E_AWS_PRIVATE_KEY_PATH: /tmp/agent-qa-aws-ssh-key
E2E_AWS_PUBLIC_KEY_PATH: /tmp/agent-qa-aws-ssh-key.pub
E2E_AZURE_PRIVATE_KEY_PATH: /tmp/agent-qa-azure-ssh-key
E2E_AZURE_PUBLIC_KEY_PATH: /tmp/agent-qa-azure-ssh-key.pub
E2E_COMMIT_SHA: $CI_COMMIT_SHORT_SHA
E2E_COVERAGE_OUT_DIR: $CI_PROJECT_DIR/coverage
E2E_GCP_PRIVATE_KEY_PATH: /tmp/agent-qa-gcp-ssh-key
E2E_GCP_PUBLIC_KEY_PATH: /tmp/agent-qa-gcp-ssh-key.pub
E2E_KEY_PAIR_NAME: datadog-agent-ci-rsa
E2E_LOGS_PROCESSING_TEST_DEPTH: 1
E2E_OUTPUT_DIR: $CI_PROJECT_DIR/e2e-output
E2E_PIPELINE_ID: $CI_PIPELINE_ID
E2E_RESULT_JSON: $CI_PROJECT_DIR/e2e_test_output.json
E2E_USE_AWS_PROFILE: 'true'
EXTERNAL_LINKS_PATH: external_links_$CI_JOB_ID.json
FLAKY_PATTERNS_CONFIG: $CI_PROJECT_DIR/flaky-patterns-runtime.yaml
GIT_STRATEGY: clone
KUBERNETES_CPU_REQUEST: 6
KUBERNETES_MEMORY_LIMIT: 16Gi
KUBERNETES_MEMORY_REQUEST: 12Gi
MAX_RETRIES_FLAG: ''
ON_NIGHTLY_FIPS: 'true'
PRE_BUILT_BINARIES_FLAG: --use-prebuilt-binaries
REMOTE_STACK_CLEANING: 'true'
SHOULD_RUN_IN_FLAKES_FINDER: 'true'
TARGETS: ./tests/containers
TEAM: container-integrationsAdded Jobsnew-e2e-containers-k8s-latestnew-e2e-containers-k8s-latest:
after_script:
- CODECOV_TOKEN=$($CI_PROJECT_DIR/tools/ci/fetch_secret.sh $CODECOV token) || exit
$?; export CODECOV_TOKEN
- $CI_PROJECT_DIR/tools/ci/junit_upload.sh "junit-${CI_JOB_ID}.tgz" "$E2E_RESULT_JSON"
- "if [ -d \"$E2E_COVERAGE_OUT_DIR\" ]; then\n dda inv -- -e coverage.process-e2e-coverage-folders\
\ $E2E_COVERAGE_OUT_DIR\n pip install boto3==1.38.8 # TODO: Remove this before\
\ merging, after dda is bumped in test-infra-definitions\n dda inv -- -e dyntest.compute-and-upload-job-index\
\ --bucket-uri $S3_PERMANENT_ARTIFACTS_URI --coverage-folder $E2E_COVERAGE_OUT_DIR\
\ --commit-sha $CI_COMMIT_SHA --job-id $CI_JOB_ID\nfi\n"
artifacts:
expire_in: 2 weeks
paths:
- $E2E_OUTPUT_DIR
- $E2E_RESULT_JSON
- junit-*.tgz
- $E2E_COVERAGE_OUT_DIR
reports:
annotations:
- $EXTERNAL_LINKS_PATH
when: always
before_script:
- mkdir -p $GOPATH/pkg/mod/cache && tar xJf modcache_e2e.tar.xz -C $GOPATH/pkg/mod/cache
- rm -f modcache_e2e.tar.xz
- mkdir -p ~/.pulumi && tar xJf pulumi_plugins.tar.xz -C ~/.pulumi
- rm -f pulumi_plugins.tar.xz
- mkdir -p $GOPATH/pkg/mod/cache && tar xJf modcache_tools.tar.xz -C $GOPATH/pkg/mod/cache
- rm -f modcache_tools.tar.xz
- dda inv -- -e install-tools
- mkdir -p ~/.aws
- "if [ -n \"$E2E_USE_AWS_PROFILE\" ]; then\n echo Using agent-qa-ci aws profile\n\
\ $CI_PROJECT_DIR/tools/ci/fetch_secret.sh $AGENT_QA_E2E profile >> ~/.aws/config\
\ || exit $?\n # Now all `aws` commands target the agent-qa profile\n export\
\ AWS_PROFILE=agent-qa-ci\nelse\n # Assume role to fetch only once credentials\
\ and avoid rate limits\n echo Assuming ddbuild-agent-ci role\n roleoutput=\"\
$(aws sts assume-role --role-arn arn:aws:iam::669783387624:role/ddbuild-agent-ci\
\ --external-id ddbuild-agent-ci --role-session-name RoleSession)\"\n export\
\ AWS_ACCESS_KEY_ID=\"$(echo \"$roleoutput\" | jq -r '.Credentials.AccessKeyId')\"\
\n export AWS_SECRET_ACCESS_KEY=\"$(echo \"$roleoutput\" | jq -r '.Credentials.SecretAccessKey')\"\
\n export AWS_SESSION_TOKEN=\"$(echo \"$roleoutput\" | jq -r '.Credentials.SessionToken')\"\
\nfi\n"
- $CI_PROJECT_DIR/tools/ci/fetch_secret.sh $AGENT_QA_E2E ssh_public_key_rsa > $E2E_AWS_PUBLIC_KEY_PATH
|| exit $?
- touch $E2E_AWS_PRIVATE_KEY_PATH && chmod 600 $E2E_AWS_PRIVATE_KEY_PATH && $CI_PROJECT_DIR/tools/ci/fetch_secret.sh
$AGENT_QA_E2E ssh_key_rsa > $E2E_AWS_PRIVATE_KEY_PATH || exit $?
- $CI_PROJECT_DIR/tools/ci/fetch_secret.sh $AGENT_QA_E2E ssh_public_key_rsa > $E2E_AZURE_PUBLIC_KEY_PATH
|| exit $?
- touch $E2E_AZURE_PRIVATE_KEY_PATH && chmod 600 $E2E_AZURE_PRIVATE_KEY_PATH &&
$CI_PROJECT_DIR/tools/ci/fetch_secret.sh $AGENT_QA_E2E ssh_key_rsa > $E2E_AZURE_PRIVATE_KEY_PATH
|| exit $?
- $CI_PROJECT_DIR/tools/ci/fetch_secret.sh $AGENT_QA_E2E ssh_public_key_rsa > $E2E_GCP_PUBLIC_KEY_PATH
|| exit $?
- touch $E2E_GCP_PRIVATE_KEY_PATH && chmod 600 $E2E_GCP_PRIVATE_KEY_PATH && $CI_PROJECT_DIR/tools/ci/fetch_secret.sh
$AGENT_QA_E2E ssh_key_rsa > $E2E_GCP_PRIVATE_KEY_PATH || exit $?
- pulumi login "s3://dd-pulumi-state?region=us-east-1&awssdk=v2&profile=$AWS_PROFILE"
- ARM_CLIENT_ID=$($CI_PROJECT_DIR/tools/ci/fetch_secret.sh $E2E_AZURE client_id)
|| exit $?; export ARM_CLIENT_ID
- ARM_CLIENT_SECRET=$($CI_PROJECT_DIR/tools/ci/fetch_secret.sh $E2E_AZURE token)
|| exit $?; export ARM_CLIENT_SECRET
- ARM_TENANT_ID=$($CI_PROJECT_DIR/tools/ci/fetch_secret.sh $E2E_AZURE tenant_id)
|| exit $?; export ARM_TENANT_ID
- ARM_SUBSCRIPTION_ID=$($CI_PROJECT_DIR/tools/ci/fetch_secret.sh $E2E_AZURE subscription_id)
|| exit $?; export ARM_SUBSCRIPTION_ID
- $CI_PROJECT_DIR/tools/ci/fetch_secret.sh $E2E_GCP credentials_json > ~/gcp-credentials.json
|| exit $?
- export GOOGLE_APPLICATION_CREDENTIALS=~/gcp-credentials.json
- dda inv -- -e gitlab.generate-ci-visibility-links --output=$EXTERNAL_LINKS_PATH
- export DD_ENV=nativetest
- export DD_CIVISIBILITY_AGENTLESS_ENABLED=true
- DD_API_KEY=$($CI_PROJECT_DIR/tools/ci/fetch_secret.sh $AGENT_API_KEY_ORG2 token)
|| exit $?; export DD_API_KEY
- export WINDOWS_DDNPM_DRIVER=${WINDOWS_DDNPM_DRIVER:-$(dda inv release.get-release-json-value
"dependencies::WINDOWS_DDNPM_DRIVER" --no-worktree)}
- export WINDOWS_DDPROCMON_DRIVER=${WINDOWS_DDPROCMON_DRIVER:-$(dda inv release.get-release-json-value
"dependencies::WINDOWS_DDPROCMON_DRIVER" --no-worktree)}
image: registry.ddbuild.io/ci/datadog-agent-buildimages/linux$CI_IMAGE_LINUX_SUFFIX:$CI_IMAGE_LINUX
needs:
- go_e2e_deps
- go_e2e_test_binaries
- go_tools_deps
- job: new-e2e-base-coverage
optional: true
- qa_agent
- qa_agent_jmx
- qa_dca
- qa_dogstatsd
rules:
- if: $RUN_E2E_TESTS == "off"
when: never
- if: $CI_COMMIT_BRANCH =~ /^mq-working-branch-/
when: never
- if: $RUN_E2E_TESTS == "on"
when: on_success
- if: $CI_COMMIT_BRANCH == "main"
when: on_success
- if: $CI_COMMIT_BRANCH =~ /^[0-9]+\.[0-9]+\.x$/
when: on_success
- if: $CI_COMMIT_TAG =~ /^[0-9]+\.[0-9]+\.[0-9]+-rc\.[0-9]+$/
when: on_success
- changes:
compare_to: $COMPARE_TO_BRANCH
paths:
- .gitlab/test/e2e/e2e.yml
- test/e2e-framework/**/*
- test/new-e2e/go.mod
- go.mod
- flakes.yaml
- release.json
- changes:
compare_to: $COMPARE_TO_BRANCH
paths:
- comp/core/tagger/**/*
- comp/core/workloadmeta/**/*
- comp/core/autodiscovery/listeners/**/*
- comp/core/autodiscovery/providers/**/*
- comp/forwarder/defaultforwarder/**/*
- comp/serializer/**/*
- pkg/aggregator/*/**
- comp/languagedetection/**/*
- pkg/clusteragent/admission/mutate/**/*
- pkg/clusteragent/languagedetection/**/*
- pkg/collector/corechecks/cluster/**/*
- pkg/collector/corechecks/containers/**/*
- pkg/collector/corechecks/containerimage/**/*
- pkg/collector/corechecks/containerlifecycle/**/*
- pkg/collector/corechecks/sbom/**/*
- pkg/sbom/**/*
- pkg/util/clusteragent/**/*
- pkg/util/containerd/**/*
- pkg/util/containers/**/*
- pkg/util/docker/**/*
- pkg/util/ecs/**/*
- pkg/util/kubernetes/**/*
- pkg/util/cgroups/**/*
- pkg/util/trivy/**/*
- test/new-e2e/tests/containers/**/*
- test/new-e2e/go.mod
- go.mod
when: on_success
- changes:
compare_to: $COMPARE_TO_BRANCH
paths:
- pkg/**/*
- cmd/**/*
- comp/**/*
when: on_success
- if: $CI_COMMIT_BRANCH =~ /^mq-working-branch-/
when: never
- allow_failure: true
when: manual
script:
- export IS_DEV_BRANCH="$(dda inv -- -e pipeline.is-dev-branch)"
- DYNAMIC_TESTS_BREAKGLASS=$($CI_PROJECT_DIR/tools/ci/fetch_secret.sh $DYNAMIC_TESTS_BREAKGLASS
value) || exit $?; export DYNAMIC_TESTS_BREAKGLASS
- "if [ \"$DYNAMIC_TESTS_BREAKGLASS\" == \"true\" ] || [ \"$IS_DEV_BRANCH\" == \"\
false\" ] || [ \"$RUN_E2E_TESTS\" == \"on\" ]; then\n export DYNAMIC_TESTS_FLAG=\"\
\"\nfi\n"
- dda inv -- -e new-e2e-tests.run $DYNAMIC_TESTS_FLAG $PRE_BUILT_BINARIES_FLAG $MAX_RETRIES_FLAG
--local-package $CI_PROJECT_DIR/$OMNIBUS_BASE_DIR --result-json $E2E_RESULT_JSON
--targets $TARGETS -c ddagent:imagePullRegistry=669783387624.dkr.ecr.us-east-1.amazonaws.com
-c ddagent:imagePullUsername=AWS -c ddagent:imagePullPassword=$(aws ecr get-login-password)
--junit-tar junit-${CI_JOB_ID}.tgz ${EXTRA_PARAMS} --test-washer --logs-folder=$E2E_OUTPUT_DIR/logs
--logs-post-processing --logs-post-processing-test-depth=$E2E_LOGS_PROCESSING_TEST_DEPTH
stage: e2e
tags:
- arch:amd64
- specific:true
variables:
DYNAMIC_TESTS_FLAG: --impacted
E2E_AWS_PRIVATE_KEY_PATH: /tmp/agent-qa-aws-ssh-key
E2E_AWS_PUBLIC_KEY_PATH: /tmp/agent-qa-aws-ssh-key.pub
E2E_AZURE_PRIVATE_KEY_PATH: /tmp/agent-qa-azure-ssh-key
E2E_AZURE_PUBLIC_KEY_PATH: /tmp/agent-qa-azure-ssh-key.pub
E2E_COMMIT_SHA: $CI_COMMIT_SHORT_SHA
E2E_COVERAGE_OUT_DIR: $CI_PROJECT_DIR/coverage
E2E_GCP_PRIVATE_KEY_PATH: /tmp/agent-qa-gcp-ssh-key
E2E_GCP_PUBLIC_KEY_PATH: /tmp/agent-qa-gcp-ssh-key.pub
E2E_KEY_PAIR_NAME: datadog-agent-ci-rsa
E2E_LOGS_PROCESSING_TEST_DEPTH: 1
E2E_OUTPUT_DIR: $CI_PROJECT_DIR/e2e-output
E2E_PIPELINE_ID: $CI_PIPELINE_ID
E2E_RESULT_JSON: $CI_PROJECT_DIR/e2e_test_output.json
E2E_USE_AWS_PROFILE: 'true'
EXTERNAL_LINKS_PATH: external_links_$CI_JOB_ID.json
EXTRA_PARAMS: --run TestKindSuite -c ddinfra:kubernetesVersion=v1.34.0@sha256:7416a61b42b1662ca6ca89f02028ac133a309a2a30ba309614e8ec94d976dc5a
FLAKY_PATTERNS_CONFIG: $CI_PROJECT_DIR/flaky-patterns-runtime.yaml
GIT_STRATEGY: clone
KUBERNETES_CPU_REQUEST: 6
KUBERNETES_MEMORY_LIMIT: 16Gi
KUBERNETES_MEMORY_REQUEST: 12Gi
MAX_RETRIES_FLAG: ''
ON_NIGHTLY_FIPS: 'true'
PRE_BUILT_BINARIES_FLAG: --use-prebuilt-binaries
REMOTE_STACK_CLEANING: 'true'
SHOULD_RUN_IN_FLAKES_FINDER: 'true'
TARGETS: ./tests/containers
TEAM: container-integrationsChanges Summary
ℹ️ Diff available in the job log. |
Contributor
Static quality checks✅ Please find below the results from static quality gates Successful checksInfo
21 successful checks with minimal change (< 2 KiB)
On-wire sizes (compressed)
|
triviajon
added
changelog/no-changelog
Regression DetectorRegression Detector ResultsMetrics dashboard Baseline: 59c4a3e Optimization Goals: ✅ No significant changes detected
|
| perf | experiment | goal | Δ mean % | Δ mean % CI | trials | links |
|---|---|---|---|---|---|---|
| ➖ | docker_containers_cpu | % cpu utilization | -2.78 | [-5.66, +0.09] | 1 | Logs |
Fine details of change detection per experiment
| perf | experiment | goal | Δ mean % | Δ mean % CI | trials | links |
|---|---|---|---|---|---|---|
| ➖ | ddot_metrics_sum_delta | memory utilization | +0.59 | [+0.37, +0.80] | 1 | Logs |
| ➖ | quality_gate_logs | % cpu utilization | +0.50 | [-0.96, +1.97] | 1 | Logs bounds checks dashboard |
| ➖ | ddot_metrics_sum_cumulative | memory utilization | +0.20 | [+0.03, +0.36] | 1 | Logs |
| ➖ | ddot_logs | memory utilization | +0.14 | [+0.08, +0.21] | 1 | Logs |
| ➖ | quality_gate_idle | memory utilization | +0.09 | [+0.05, +0.13] | 1 | Logs bounds checks dashboard |
| ➖ | ddot_metrics_sum_cumulativetodelta_exporter | memory utilization | +0.05 | [-0.18, +0.29] | 1 | Logs |
| ➖ | quality_gate_idle_all_features | memory utilization | +0.05 | [+0.01, +0.09] | 1 | Logs bounds checks dashboard |
| ➖ | file_to_blackhole_500ms_latency | egress throughput | +0.05 | [-0.34, +0.43] | 1 | Logs |
| ➖ | file_to_blackhole_1000ms_latency | egress throughput | +0.05 | [-0.37, +0.46] | 1 | Logs |
| ➖ | uds_dogstatsd_to_api_v3 | ingress throughput | +0.02 | [-0.10, +0.14] | 1 | Logs |
| ➖ | file_tree | memory utilization | +0.00 | [-0.05, +0.05] | 1 | Logs |
| ➖ | tcp_dd_logs_filter_exclude | ingress throughput | +0.00 | [-0.09, +0.09] | 1 | Logs |
| ➖ | uds_dogstatsd_to_api | ingress throughput | -0.01 | [-0.14, +0.13] | 1 | Logs |
| ➖ | file_to_blackhole_0ms_latency | egress throughput | -0.02 | [-0.54, +0.50] | 1 | Logs |
| ➖ | file_to_blackhole_100ms_latency | egress throughput | -0.03 | [-0.08, +0.01] | 1 | Logs |
| ➖ | quality_gate_metrics_logs | memory utilization | -0.22 | [-0.45, -0.00] | 1 | Logs bounds checks dashboard |
| ➖ | uds_dogstatsd_20mb_12k_contexts_20_senders | memory utilization | -0.25 | [-0.31, -0.19] | 1 | Logs |
| ➖ | otlp_ingest_logs | memory utilization | -0.29 | [-0.39, -0.19] | 1 | Logs |
| ➖ | ddot_metrics | memory utilization | -0.29 | [-0.51, -0.07] | 1 | Logs |
| ➖ | tcp_syslog_to_blackhole | ingress throughput | -0.35 | [-0.41, -0.29] | 1 | Logs |
| ➖ | docker_containers_memory | memory utilization | -0.49 | [-0.56, -0.42] | 1 | Logs |
| ➖ | otlp_ingest_metrics | memory utilization | -0.52 | [-0.67, -0.36] | 1 | Logs |
| ➖ | docker_containers_cpu | % cpu utilization | -2.78 | [-5.66, +0.09] | 1 | Logs |
Bounds Checks: ✅ Passed
| perf | experiment | bounds_check_name | replicates_passed | links |
|---|---|---|---|---|
| ✅ | docker_containers_cpu | simple_check_run | 10/10 | |
| ✅ | docker_containers_memory | memory_usage | 10/10 | |
| ✅ | docker_containers_memory | simple_check_run | 10/10 | |
| ✅ | file_to_blackhole_0ms_latency | lost_bytes | 10/10 | |
| ✅ | file_to_blackhole_0ms_latency | memory_usage | 10/10 | |
| ✅ | file_to_blackhole_1000ms_latency | lost_bytes | 10/10 | |
| ✅ | file_to_blackhole_1000ms_latency | memory_usage | 10/10 | |
| ✅ | file_to_blackhole_100ms_latency | lost_bytes | 10/10 | |
| ✅ | file_to_blackhole_100ms_latency | memory_usage | 10/10 | |
| ✅ | file_to_blackhole_500ms_latency | lost_bytes | 10/10 | |
| ✅ | file_to_blackhole_500ms_latency | memory_usage | 10/10 | |
| ✅ | quality_gate_idle | intake_connections | 10/10 | bounds checks dashboard |
| ✅ | quality_gate_idle | memory_usage | 10/10 | bounds checks dashboard |
| ✅ | quality_gate_idle_all_features | intake_connections | 10/10 | bounds checks dashboard |
| ✅ | quality_gate_idle_all_features | memory_usage | 10/10 | bounds checks dashboard |
| ✅ | quality_gate_logs | intake_connections | 10/10 | bounds checks dashboard |
| ✅ | quality_gate_logs | lost_bytes | 10/10 | bounds checks dashboard |
| ✅ | quality_gate_logs | memory_usage | 10/10 | bounds checks dashboard |
| ✅ | quality_gate_metrics_logs | cpu_usage | 10/10 | bounds checks dashboard |
| ✅ | quality_gate_metrics_logs | intake_connections | 10/10 | bounds checks dashboard |
| ✅ | quality_gate_metrics_logs | lost_bytes | 10/10 | bounds checks dashboard |
| ✅ | quality_gate_metrics_logs | memory_usage | 10/10 | bounds checks dashboard |
Explanation
Confidence level: 90.00%
Effect size tolerance: |Δ mean %| ≥ 5.00%
Performance changes are noted in the perf column of each table:
- ✅ = significantly better comparison variant performance
- ❌ = significantly worse comparison variant performance
- ➖ = no significant change in performance
A regression test is an A/B test of target performance in a repeatable rig, where "performance" is measured as "comparison variant minus baseline variant" for an optimization goal (e.g., ingress throughput). Due to intrinsic variability in measuring that goal, we can only estimate its mean value for each experiment; we report uncertainty in that value as a 90.00% confidence interval denoted "Δ mean % CI".
For each experiment, we decide whether a change in performance is a "regression" -- a change worth investigating further -- if all of the following criteria are true:
-
Its estimated |Δ mean %| ≥ 5.00%, indicating the change is big enough to merit a closer look.
-
Its 90.00% confidence interval "Δ mean % CI" does not contain zero, indicating that if our statistical model is accurate, there is at least a 90.00% chance there is a difference in performance between baseline and comparison variants.
-
Its configuration does not mark it "erratic".
Replicate Execution Details
We run multiple replicates for each experiment/variant. However, we allow replicates to be automatically retried if there are any failures, up to 8 times, at which point the replicate is marked dead and we are unable to run analysis for the entire experiment. We call each of these attempts at running replicates a replicate execution. This section lists all replicate executions that failed due to the target crashing or being oom killed.
Note: In the below tables we bucket failures by experiment, variant, and failure type. For each of these buckets we list out the replicate indexes that failed with an annotation signifying how many times said replicate failed with the given failure mode. In the below example the baseline variant of the experiment named experiment_with_failures had two replicates that failed by oom kills. Replicate 0, which failed 8 executions, and replicate 1 which failed 6 executions, all with the same failure mode.
| Experiment | Variant | Replicates | Failure | Logs | Debug Dashboard |
|---|---|---|---|---|---|
| experiment_with_failures | baseline | 0 (x8) 1 (x6) | Oom killed | Debug Dashboard |
The debug dashboard links will take you to a debugging dashboard specifically designed to investigate replicate execution failures.
❌ Retried Profiling Replicate Execution Failures (target internal profiling)
Note: Profiling replicas may still be executing. See the debug dashboard for up to date status.
| Experiment | Variant | Replicates | Failure | Debug Dashboard |
|---|---|---|---|---|
| quality_gate_idle_all_features | baseline | 11 (x4) | Oom killed | Debug Dashboard |
| quality_gate_idle_all_features | comparison | 11 (x4) | Oom killed | Debug Dashboard |
CI Pass/Fail Decision
✅ Passed. All Quality Gates passed.
- quality_gate_idle_all_features, bounds check memory_usage: 10/10 replicas passed. Gate passed.
- quality_gate_idle_all_features, bounds check intake_connections: 10/10 replicas passed. Gate passed.
- quality_gate_logs, bounds check intake_connections: 10/10 replicas passed. Gate passed.
- quality_gate_logs, bounds check memory_usage: 10/10 replicas passed. Gate passed.
- quality_gate_logs, bounds check lost_bytes: 10/10 replicas passed. Gate passed.
- quality_gate_idle, bounds check memory_usage: 10/10 replicas passed. Gate passed.
- quality_gate_idle, bounds check intake_connections: 10/10 replicas passed. Gate passed.
- quality_gate_metrics_logs, bounds check memory_usage: 10/10 replicas passed. Gate passed.
- quality_gate_metrics_logs, bounds check lost_bytes: 10/10 replicas passed. Gate passed.
- quality_gate_metrics_logs, bounds check cpu_usage: 10/10 replicas passed. Gate passed.
- quality_gate_metrics_logs, bounds check intake_connections: 10/10 replicas passed. Gate passed.
lavigne958
approved these changes
Jan 7, 2026
justin-lesko
approved these changes
Jan 7, 2026
frank-spano
approved these changes
Jan 12, 2026
triviajon
force-pushed
the
triviajon/CONTINT-4925/k8s-latest-e2e-job
branch
from
8648252 to
134abcc
Compare
triviajon
force-pushed
the
triviajon/CONTINT-4925/k8s-latest-e2e-job
branch
from
134abcc to
bd4309d
Compare
KevinFairise2
approved these changes
Jan 15, 2026
Contributor
Author
|
/merge |
|
View all feedbacks in Devflow UI.
This pull request is not mergeable according to GitHub. Common reasons include pending required checks, missing approvals, or merge conflicts — but it could also be blocked by other repository rules or settings.
The expected merge time in
|
dd-mergequeue
bot
deleted the
triviajon/CONTINT-4925/k8s-latest-e2e-job
branch
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
5 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What does this PR do?
This PR modifies the
new-e2e-containersjob and adds anew-e2e-containers-k8s-latestjob to the E2E workflow. Specifically:new-e2e-containers-k8s-latestjob that always runs against the latest K8s version from Dockerhub.new-e2e-containers-k8s-latestjob with the new latest version.This leaves the
new-e2e-containersas a designated area where we will pin K8s versions that we have special interest in maintaining support for.Motivation
https://datadoghq.atlassian.net/browse/CONTINT-4925
Specifically, this will make it easier to setup monitors about the latest version.
Describe how you validated your changes
Running the commands in the
update-kubernetes-versions.ymlworkflow:Additional Notes